Densitometric and local histogram based analysis of computed tomography images in patients with idiopathic pulmonary fibrosis

Quantitative CT analysis of idiopathic pulmonary fibrosis and correlation with lung function study

BACKGROUND

Idiopathic Pulmonary Fibrosis (IPF) is a progressive fibrotic lung disease. However, the field of quantitative CT scan analysis in conjunction with pulmonary function test for IPF patients remains relatively understudied. In this study, we evaluated the diagnostic value of features derived high-resolution computed tomography (HRCT) for patients with IPF and correlated them with pulmonary function tests.

METHODS

We retrospectively analyzed the chest HRCT images and pulmonary function test results of 52 patients with IPF during the same period (1 week) and selected 52 healthy individuals, matched for sex, age, and body mass index (BMI) and with normal chest HRCT as controls. HRCT scans were performed using a Philips 256-row Brilliance iCT scanner with standardized parameters. Lung function tests were performed using a Jaeger volumetric tracer for forced vital capacity (FVC), total lung capacity (TLC), forced expiratory volume in first second (FEV1), FEV1/FVC, carbon monoxide diffusing capacity (DLCO), and maximum ventilation volume (MVV) metrics. CT quantitative analysis, including tissue segmentation and threshold-based quantification of lung abnormalities, was performed using 3D-Slicer software to calculate the percentage of normal lung areas (NL%), percentage of ground-glass opacity areas (GGO%), percentage of fibrotic area (F%) and abnormal lesion area percentage (AA%). Semi-quantitative analyses were performed by two experienced radiologists to assess disease progression. The aortic-to-sternal distance (ASD) was measured on axial images as a standardized parameter. Spearman or Pearson correlation analysis and multivariate stepwise linear regression were used to analyze the relationship between the data in each group, and the ROC curve was used to determine the optimal quantitative CT metrics for identifying IPF and controls.

RESULTS

ROC curve analysis showed that F% distinguished the IPF patient group from the control group with the largest area under the curve (AUC) of 0.962 (95% confidence interval: 0.85-0.96). Additionally, with F% = 4.05% as the threshold, the Youden's J statistic was 0.827, with a sensitivity of 92.3% and a specificity of 90.4%. The ASD was significantly lower in the late stage of progression than in the early stage (t = 5.691, P < 0.001), with a mean reduction of 2.45% per month. Quantitative CT indices correlated with all pulmonary function parameters except FEV1/FVC, with the highest correlation coefficients observed for F% and TLC%, FEV1%, FVC%, MVV% (r = - 0.571, - 0.520, - 0.521, - 0.555, respectively, all P-values < 0.001), and GGO% was significantly correlated with DLCO% (r = - 0.600, P < 0.001). Multiple stepwise linear regression analysis showed that F% was the best predictor of TLC%, FEV1%, FVC%, and MVV% (R2 = 0.301, 0.301, 0.300, and 0.302, respectively, all P-values < 0.001), and GGO% was the best predictor of DLCO% (R2 = 0.360, P < 0.001).

CONCLUSIONS

Quantitative CT analysis can be used to diagnose IPF and assess lung function impairment. A decrease in the ASD may indicate disease progression.

From pixels to prognosis: unlocking the potential of deep learning in fibrotic lung disease imaging analysis

The licensing of antifibrotic therapy for fibrotic lung diseases, including idiopathic pulmonary fibrosis (IPF), has created an urgent need for reliable biomarkers to predict disease progression and treatment response. Some patients experience stable disease trajectories, while others deteriorate rapidly, making treatment decisions challenging. High-resolution chest CT has become crucial for diagnosis, but visual assessments by radiologists suffer from low reproducibility and high interobserver variability. To address these issues, computer-based image analysis, called quantitative CT, has emerged. However, many quantitative CT methods rely on human input for training, therefore potentially incorporating human error into computer training. Rapid advances in artificial intelligence, specifically deep learning, aim to overcome this limitation by enabling autonomous quantitative analysis. While promising, deep learning also presents challenges including the need to minimize algorithm biases, ensuring explainability, and addressing accessibility and ethical concerns. This review explores the development and application of deep learning in improving the imaging process for fibrotic lung disease.

Clinically Relevant Biomarkers in Connective Tissue Disease-Associated Interstitial Lung Disease

Interstitial lung disease (ILD) complicates connective tissue disease (CTD) with variable incidence and is a leading cause of death in these patients. To improve CTD-ILD outcomes, early recognition and management of ILD is critical. Blood-based and radiologic biomarkers that assist in the diagnosis CTD-ILD have long been studied. Recent studies, including -omic investigations, have also begun to identify biomarkers that may help prognosticate such patients. This review provides an overview of clinically relevant biomarkers in patients with CTD-ILD, highlighting recent advances to assist in the diagnosis and prognostication of CTD-ILD.

Subchronic particulate matter exposure underlying polyhexamethylene guanidine phosphate-induced lung injury: Quantitative and qualitative evaluation with chest computed tomography

Our study was to explore the effects of subchronic particulate matter (PM) exposure on lung injury induced by polyhexamethylene guanidine phosphate (PHMG-p) in a rat model. Specifically, we investigated pulmonary inflammation, fibrosis, and tumor formation using chest computed tomography (CT), and histopathologic examination. PHMG-p was administered intratracheally to 20 male rats. After an initial week of PHMG-p treatment, the experimental group (PM group) received intratracheal administration of PM suspension, while the control group received normal saline. This regimen was continued for 10 weeks to induce subchronic PM exposure. Chest CT scans were conducted on all rats, followed by the extraction of both lungs for histopathological analysis. All CT images underwent comprehensive quantitative and qualitative analyses. Pulmonary inflammation was markedly intensified in rats subjected to subchronic PM exposure in the PM group compared to those in the control. Similarly, lung fibrosis was more severe in the PM group as observed on both chest CT and histopathologic examination. Quantitative chest CT analysis revealed that the mean lesion volume was significantly greater in the PM group than in the control group. Although the incidence of bronchiolo-alveolar hyperplasia was higher in the PM group compared to the control group, this difference was not statistically significant. In summary, subchronic PM exposure exacerbated pulmonary inflammation and fibrosis underlying lung injury induced by PHMG-p.

Deep learning-based prognostication in idiopathic pulmonary fibrosis using chest radiographs

OBJECTIVES

To develop and validate a deep learning-based prognostic model in patients with idiopathic pulmonary fibrosis (IPF) using chest radiographs.

METHODS

To develop a deep learning-based prognostic model using chest radiographs (DLPM), the patients diagnosed with IPF during 2011-2021 were retrospectively collected and were divided into training (n = 1007), validation (n = 117), and internal test (n = 187) datasets. Up to 10 consecutive radiographs were included for each patient. For external testing, three cohorts from independent institutions were collected (n = 152, 141, and 207). The discrimination performance of DLPM was evaluated using areas under the time-dependent receiver operating characteristic curves (TD-AUCs) for 3-year survival and compared with that of forced vital capacity (FVC). Multivariable Cox regression was performed to investigate whether the DLPM was an independent prognostic factor from FVC. We devised a modified gender-age-physiology (GAP) index (GAP-CR), by replacing DLCO with DLPM.

RESULTS

DLPM showed similar-to-higher performance at predicting 3-year survival than FVC in three external test cohorts (TD-AUC: 0.83 [95% CI: 0.76-0.90] vs. 0.68 [0.59-0.77], p < 0.001; 0.76 [0.68-0.85] vs. 0.70 [0.60-0.80], p = 0.21; 0.79 [0.72-0.86] vs. 0.76 [0.69-0.83], p = 0.41). DLPM worked as an independent prognostic factor from FVC in all three cohorts (ps < 0.001). The GAP-CR index showed a higher 3-year TD-AUC than the original GAP index in two of the three external test cohorts (TD-AUC: 0.85 [0.80-0.91] vs. 0.79 [0.72-0.86], p = 0.02; 0.72 [0.64-0.80] vs. 0.69 [0.61-0.78], p = 0.56; 0.76 [0.69-0.83] vs. 0.68 [0.60-0.76], p = 0.01).

CONCLUSIONS

A deep learning model successfully predicted survival in patients with IPF from chest radiographs, comparable to and independent of FVC.

CLINICAL RELEVANCE STATEMENT

Deep learning-based prognostication from chest radiographs offers comparable-to-higher prognostic performance than forced vital capacity.

KEY POINTS

• A deep learning-based prognostic model for idiopathic pulmonary fibrosis was developed using 6063 radiographs. • The prognostic performance of the model was comparable-to-higher than forced vital capacity, and was independent from FVC in all three external test cohorts. • A modified gender-age-physiology index replacing diffusing capacity for carbon monoxide with the deep learning model showed higher performance than the original index in two external test cohorts.

Evaluating Tissue Heterogeneity in the Radiologically Normal-Appearing Tissue in IPF Compared to Healthy Controls

RATIONALE AND OBJECTIVES

Idiopathic Pulmonary Fibrosis (IPF) is a progressive interstitial lung disease characterised by heterogeneously distributed fibrotic lesions. The inter- and intra-patient heterogeneity of the disease has meant that useful biomarkers of severity and progression have been elusive. Previous quantitative computed tomography (CT) based studies have focussed on characterising the pathological tissue. However, we hypothesised that the remaining lung tissue, which appears radiologically normal, may show important differences from controls in tissue characteristics.

MATERIALS AND METHODS

Quantitative metrics were derived from CT scans in IPF patients (N = 20) and healthy controls with a similar age (N = 59). An automated quantitative software (CALIPER, Computer-Aided Lung Informatics for Pathology Evaluation and Rating) was used to classify tissue as normal-appearing, fibrosis, or low attenuation area. Densitometry metrics were calculated for all lung tissue and for only the normal-appearing tissue. Heterogeneity of lung tissue density was quantified as coefficient of variation and by quadtree. Associations between measured lung function and quantitative metrics were assessed and compared between the two cohorts.

RESULTS

All metrics were significantly different between controls and IPF (p < 0.05), including when only the normal tissue was evaluated (p < 0.04). Density in the normal tissue was 14% higher in the IPF participants than controls (p < 0.001). The normal-appearing tissue in IPF had heterogeneity metrics that exhibited significant positive relationships with the percent predicted diffusion capacity for carbon monoxide.

CONCLUSION

We provide quantitative assessment of IPF lung tissue characteristics compared to a healthy control group of similar age. Tissue that appears visually normal in IPF exhibits subtle but quantifiable differences that are associated with lung function and gas exchange.

Longitudinal long term follow up investigation on the carcinogenic impact of polyhexamethylene guanidine phosphate in rat models

Polyhexamethylene guanidine phosphate (PHMG-p) is a major component in humidifier disinfectants, which cause life-threatening lung injuries. However, to our knowledge, no published studies have investigated associations between PHMG-p dose and lung damage severity with long-term follow-up. Therefore, we evaluated longitudinal dose-dependent changes in lung injuries using repeated chest computed tomography (CT). Rats were exposed to low (0.2 mg/kg, n = 10), intermediate (1.0 mg/kg, n = 10), and high (5.0 mg/kg, n = 10) doses of PHMG-p. All rats underwent repeated CT scans after 10 and 40 weeks following the first exposure. All CT images were quantitatively analyzed using commercial software. Inflammation/fibrosis and tumor counts underwent histopathological evaluation. In both radiological and histopathologic results, the lung damage severity increased as the PHMG-p dose increased. Moreover, the number, size, and malignancy of the lung tumors increased as the dose increased. Bronchiolar-alveolar hyperplasia developed in all groups. During follow-up, there was intergroup variation in bronchiolar-alveolar hyperplasia progression, although bronchiolar-alveolar adenomas or carcinomas usually increase in size over time. Thirty-three carcinomas were detected in the high-dose group in two rats. Overall, lung damage from PHMG-p and the number and malignancy of lung tumors were shown to be dose-dependent in a rat model using repeated chest CT scans during a long-term follow-up.

Rheumatoid arthritis, quantitative parenchymal lung features, and mortality among smokers

OBJECTIVES

There have been limited investigations of the prevalence and mortality impact of quantitative computed tomography (QCT) parenchymal lung features in rheumatoid arthritis (RA). We examined the cross-sectional prevalence and mortality associations of QCT features, comparing RA and non-RA participants.

METHODS

We identified participants with and without RA in COPDGene, a multicentre cohort study of current or former smokers. Using a k-nearest neighbor quantifier, high resolution CT chest scans were scored for percentage of normal lung, interstitial changes, and emphysema. We examined associations between QCT features and RA using multivariable linear regression. After dichotomizing participants at the 75th percentile for each QCT feature among non-RA participants, we investigated mortality associations by RA/non-RA status and quartile 4 vs quartiles 1-3 of QCT features using Cox regression. We assessed for statistical interactions between RA and QCT features.

RESULTS

We identified 82 RA cases and 8820 non-RA comparators. In multivariable linear regression, RA was associated with higher percentage of interstitial changes (β = 1.7 ± 0.5, p= 0.0008) but not emphysema (β = 1.3 ± 1.7, p= 0.44). Participants with RA and >75th percentile of emphysema had significantly higher mortality than non-RA participants (HR 5.86, 95%CI 3.75-9.13) as well as RA participants (HR 5.56, 95%CI 2.71-11.38) with ≤75th percentile of emphysema. There were statistical interactions between RA and emphysema for mortality (multiplicative p= 0.014; attributable proportion 0.53, 95%CI 0.30-0.70).

CONCLUSIONS

Using machine learning-derived QCT data in a cohort of smokers, RA was associated with higher percentage of interstitial changes. The combination of RA and emphysema conferred >5-fold higher mortality.

Analysis of tissue lipidomics and computed tomography pulmonary fat attenuation volume (CTPFAV ) in idiopathic pulmonary fibrosis

BACKGROUND AND OBJECTIVE

There is increasing interest in the role of lipids in processes that modulate lung fibrosis with evidence of lipid deposition in idiopathic pulmonary fibrosis (IPF) histological specimens. The aim of this study was to identify measurable markers of pulmonary lipid that may have utility as IPF biomarkers.

STUDY DESIGN AND METHODS

IPF and control lung biopsy specimens were analysed using a unbiased lipidomic approach. Pulmonary fat attenuation volume (PFAV) was assessed on chest CT images (CTPFAV ) with 3D semi-automated lung density software. Aerated lung was semi-automatically segmented and CTPFAV calculated using a Hounsfield-unit (-40 to -200HU) threshold range expressed as a percentage of total lung volume. CTPFAV was compared to pulmonary function, serum lipids and qualitative CT fibrosis scores.

RESULTS

There was a significant increase in total lipid content on histological analysis of IPF lung tissue (23.16 nmol/mg) compared to controls (18.66 mol/mg, p = 0.0317). The median CTPFAV in IPF was higher than controls (1.34% vs. 0.72%, p < 0.001) and CTPFAV correlated significantly with DLCO% predicted (R2  = 0.356, p < 0.0001) and FVC% predicted (R2  = 0.407, p < 0.0001) in patients with IPF. CTPFAV correlated with CT features of fibrosis; higher CTPFAV was associated with >10% reticulation (1.6% vs. 0.94%, p = 0.0017) and >10% honeycombing (1.87% vs. 1.12%, p = 0.0003). CTPFAV showed no correlation with serum lipids.

CONCLUSION

CTPFAV is an easily quantifiable non-invasive measure of pulmonary lipids. In this pilot study, CTPFAV correlates with pulmonary function and radiological features of IPF and could function as a potential biomarker for IPF disease severity assessment.

Recent Advancements in Computed Tomography Assessment of Fibrotic Interstitial Lung Diseases

Interstitial lung disease (ILD) is a heterogeneous group of disorders with complex and varied imaging manifestations and prognosis. High-resolution computed tomography (HRCT) is the current standard-of-care imaging tool for ILD assessment. However, visual evaluation of HRCT is limited by interobserver variation and poor sensitivity for subtle changes. Such challenges have led to tremendous recent research interest in objective and reproducible methods to examine ILDs. Computer-aided CT analysis to include texture analysis and machine learning methods have recently been shown to be viable supplements to traditional visual assessment through improved characterization and quantification of ILDs. These quantitative tools have not only been shown to correlate well with pulmonary function tests and patient outcomes but are also useful in disease diagnosis, surveillance and management. In this review, we provide an overview of recent computer-aided tools in diagnosis, prognosis, and longitudinal evaluation of fibrotic ILDs, while outlining some of the pitfalls and challenges that have precluded further advancement of these tools as well as potential solutions and further endeavors.

Histogram-based analysis in progressive pulmonary fibrosis: relationships between pulmonary functional tests and HRCT indexes

OBJECTIVES

To investigate relationships between histogram-based high-resolution CT (HRCT) indexes and pulmonary function tests (PFTs) in interstitial lung diseases.

METHODS

Forty-nine patients having baseline and 1-year HRCT examinations and PFTs were investigated. Histogram-based HRCT indexes were calculated; strength of associations with PFTs was investigated using Pearson correlation. Patients were divided into progressive and non-progressive groups. HRCT indexes were compared between the two groups using the U-test; within each group, baseline and follow-up Wilcoxon analysis was performed. Receiver operating characteristic analysis was used for predicting disease progression.

RESULTS

At baseline, moderate correlations were observed considering kurtosis and diffusion capacity of the lungs for carbon monoxide (DLCO) (r = 0.54) and skewness and DLCO (r = 0.559), whereas weak but significant correlations were observed between forced vital capacity and kurtosis (r = 0.368, p = 0.009) and forced vital capacity and skewness (r = 0.391, p = 0.005). Negative correlations were reported between HAA% and PFTs (from r = -0.418 up to r = -0.507). At follow-up correlations between quantitative indexes and PFTs were also moderate, except for high attenuation area (HAA)% -700 and DLCO (r = -0.397). In progressive subgroup, moderate and strong correlations were found between DLCO and HRCT indexes (r = 0.595 kurtosis, r = 0.672 skewness, r=-0. 598 HAA% -600 and r = -0.626 HAA% -700). At follow-up, we observed significant differences between the two groups for kurtosis (p = 0.029), HAA% -600 (p = 0.04) and HAA% -700 (p = 0.02). To predict progression, ROC analysis reported sensitivity of 90.9% and specificity of 51.9% using a threshold value of δ kurtosis <0.03.

CONCLUSION

At one year, moderate correlations suggest that progression could be assessed through HRCT quantification.

ADVANCES IN KNOWLEDGE

This study promotes histogram-based HRCT indexes in the assessment of progressive pulmonary fibrosis.

Measure of lung dielectric proprieties in patients with Idiopathic Pulmonary Fibrosis: correlation with clinical, radiological and pulmonary functional parameters

BACKGROUND

Dielectric properties of biological tissues are biophysical parameters; in lung they change with amount of air, blood and parenchyma. Remote Dielectric Sensing (ReDS™) technology measures dielectric properties of lung tissues quantifying the content of fluids inside the scan volume. We aimed to evaluate the reliability of ReDS™ measure in Idiopathic Pulmonary Fibrosis (IPF) patients and in healthy volunteers, and to investigate the correlation of ReDS™ score with clinical, radiological and functional parameters.

METHODS

We conducted a prospective observational study, including 52 patients with diagnosis of IPF and 17 healthy volunteers; for each patient we recorded: complete functional evaluation, dyspnoea score (mMRC scale), Usual Interstitial Pneumonia (UIP) Computed Tomography (CT) pattern (UIP definite or probable) and ReDS™ measure (expressed in %).

RESULTS

ReDS™ measure was reported as correct both in patients and controls, the firsts with higher scores (33.8% vs 29.1%, p = 0.003). In IPF patients we observed a significant inverse correlation with ReDS™ score and Forced Vital Capacity (FVC), Vital Capacity (VC) and Total Lung Capacity (TLC) measures and, when we considered only patients with UIP definite CT pattern, the correlation was inverse with FVC, VC, TLC, DLCO. In IPF patients the higher was mMRC dyspnoea index, the higher was ReDS™ score. No significant correlations were observed between ReDS™ score and functional parameters in healthy controls.

DISCUSSION

We demonstrated a correlation of ReDS™ scores with some functional (mainly indicative or diagnostic for restriction) and clinical parameters in IPF patients; the score was correlated with density of tissues possibly quantifying tissue fibrosis in IPF patients.

Deep Learning Assessment of Progression of Emphysema and Fibrotic Interstitial Lung Abnormality

Rationale: Although studies have evaluated emphysema and fibrotic interstitial lung abnormality individually, less is known about their combined progression. Objectives: To define clinically meaningful progression of fibrotic interstitial lung abnormality in smokers without interstitial lung disease and evaluate the effects of fibrosis and emphysema progression on mortality. Methods: Emphysema and pulmonary fibrosis were assessed on the basis of baseline and 5-year follow-up computed tomography scans of 4,450 smokers in the COPDGene Study using deep learning algorithms. Emphysema was classified as absent, trace, mild, moderate, confluent, or advanced destructive. Fibrosis was expressed as a percentage of lung volume. Emphysema progression was defined as an increase by at least one grade. A hybrid distribution and anchor-based method was used to determine the minimal clinically important difference in fibrosis. The relationship between progression and mortality was evaluated using multivariable shared frailty models using an age timescale. Measurements and Main Results: The minimal clinically important difference for fibrosis was 0.58%. On the basis of this threshold, 2,822 (63%) had progression of neither emphysema nor fibrosis, 841 (19%) had emphysema progression alone, 512 (12%) had fibrosis progression alone, and 275 (6.2%) had progression of both. Compared with nonprogressors, hazard ratios for mortality were 1.42 (95% confidence interval, 1.11-1.82) in emphysema progressors, 1.49 (1.14-1.94) in fibrosis progressors, and 2.18 (1.58-3.02) in those with progression of both emphysema and fibrosis. Conclusions: In smokers without known interstitial lung disease, small changes in fibrosis may be clinically significant, and combined progression of emphysema and fibrosis is associated with increased mortality.

Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software

Background

Improvement in recognition and referral of pulmonary fibrosis (PF) is vital to improving patient outcomes within interstitial lung disease. We determined the performance metrics and processing time of an artificial intelligence triage and notification software, ScreenDx-LungFibrosis™, developed to improve detection of PF.

Methods

ScreenDx-LungFibrosis™ was applied to chest computed tomography (CT) scans from multisource data. Device output (+/- PF) was compared to clinical diagnosis (+/- PF), and diagnostic performance was evaluated. Primary endpoints included device sensitivity and specificity > 80% and processing time < 4.5 min.

Results

Of 3,018 patients included, PF was present in 22.9%. ScreenDx-LungFibrosis™ detected PF with a sensitivity and specificity of 91.3% (95% confidence interval (CI): 89.0-93.3%) and 95.1% (95% CI: 94.2-96.0%), respectively. Mean processing time was 27.6 s (95% CI: 26.0 - 29.1 s).

Conclusions

ScreenDx-LungFibrosis™ accurately and reliably identified PF with a rapid per-case processing time, underscoring its potential for transformative improvement in PF outcomes when routinely applied to chest CTs.

Quantitative CT Metrics Associated with Variability in the Diffusion Capacity of the Lung of Post-COVID-19 Patients with Minimal Residual Lung Lesions

(1) Background: A reduction in the diffusion capacity of the lung for carbon monoxide is a prevalent longer-term consequence of COVID-19 infection. In patients who have zero or minimal residual radiological abnormalities in the lungs, it has been debated whether the cause was mainly due to a reduced alveolar volume or involved diffuse interstitial or vascular abnormalities. (2) Methods: We performed a cross-sectional study of 45 patients with either zero or minimal residual lesions in the lungs (total volume < 7 cc) at two months to one year post COVID-19 infection. There was considerable variability in the diffusion capacity of the lung for carbon monoxide, with 27% of the patients at less than 80% of the predicted reference. We investigated a set of independent variables that may affect the diffusion capacity of the lung, including demographic, pulmonary physiology and CT (computed tomography)-derived variables of vascular volume, parenchymal density and residual lesion volume. (3) Results: The leading three variables that contributed to the variability in the diffusion capacity of the lung for carbon monoxide were the alveolar volume, determined via pulmonary function tests, the blood vessel volume fraction, determined via CT, and the parenchymal radiodensity, also determined via CT. These factors explained 49% of the variance of the diffusion capacity, with p values of 0.031, 0.005 and 0.018, respectively, after adjusting for confounders. A multiple-regression model combining these three variables fit the measured values of the diffusion capacity, with R = 0.70 and p < 0.001. (4) Conclusions: The results are consistent with the notion that in some post-COVID-19 patients, after their pulmonary lesions resolve, diffuse changes in the vascular and parenchymal structures, in addition to a low alveolar volume, could be contributors to a lingering low diffusion capacity.

Beyond Visual Interpretation: Quantitative Analysis and Artificial Intelligence in Interstitial Lung Disease Diagnosis "Expanding Horizons in Radiology"

Diffuse lung disorders (DLDs) and interstitial lung diseases (ILDs) are pathological conditions affecting the lung parenchyma and interstitial network. There are approximately 200 different entities within this category. Radiologists play an increasingly important role in diagnosing and monitoring ILDs, as they can provide non-invasive, rapid, and repeatable assessments using high-resolution computed tomography (HRCT). HRCT offers a detailed view of the lung parenchyma, resembling a low-magnification anatomical preparation from a histological perspective. The intrinsic contrast provided by air in HRCT enables the identification of even the subtlest morphological changes in the lung tissue. By interpreting the findings observed on HRCT, radiologists can make a differential diagnosis and provide a pattern diagnosis in collaboration with the clinical and functional data. The use of quantitative software and artificial intelligence (AI) further enhances the analysis of ILDs, providing an objective and comprehensive evaluation. The integration of "meta-data" such as demographics, laboratory, genomic, metabolomic, and proteomic data through AI could lead to a more comprehensive clinical and instrumental profiling beyond the human eye's capabilities.

Exploring computer-based imaging analysis in interstitial lung disease: opportunities and challenges

The advent of quantitative computed tomography (QCT) and artificial intelligence (AI) using high-resolution computed tomography data has revolutionised the way interstitial diseases are studied. These quantitative methods provide more accurate and precise results compared to prior semiquantitative methods, which were limited by human error such as interobserver disagreement or low reproducibility. The integration of QCT and AI and the development of digital biomarkers has facilitated not only diagnosis but also prognostication and prediction of disease behaviour, not just in idiopathic pulmonary fibrosis in which they were initially studied, but also in other fibrotic lung diseases. These tools provide reproducible, objective prognostic information which may facilitate clinical decision-making. However, despite the benefits of QCT and AI, there are still obstacles that need to be addressed. Important issues include optimal data management, data sharing and maintenance of data privacy. In addition, the development of explainable AI will be essential to develop trust within the medical community and facilitate implementation in routine clinical practice.

Clinically Relevant Biomarkers in Connective Tissue Disease-Associated Interstitial Lung Disease

Interstitial lung disease (ILD) complicates connective tissue disease (CTD) with variable incidence and is a leading cause of death in these patients. To improve CTD-ILD outcomes, early recognition and management of ILD is critical. Blood-based and radiologic biomarkers that assist in the diagnosis CTD-ILD have long been studied. Recent studies, including -omic investigations, have also begun to identify biomarkers that may help prognosticate such patients. This review provides an overview of clinically relevant biomarkers in patients with CTD-ILD, highlighting recent advances to assist in the diagnosis and prognostication of CTD-ILD.

Computed tomography measure of lung injury and future interstitial features: the CARDIA Lung Study

Introduction

Visually normal areas of the lung with high attenuation on computed tomography (CT) imaging, termed CT lung injury, may represent injured but not yet remodelled lung parenchyma. This prospective cohort study examined if CT lung injury is associated with future interstitial features on CT and restrictive spirometry abnormality among participants from the Coronary Artery Risk Development in Young Adults (CARDIA) study.

Methods

CARDIA is a population-based cohort study. CT scans obtained at two time points were assessed objectively for amount of lung tissue characterised as CT lung injury and interstitial features. Restrictive spirometry was defined as having a forced vital capacity (FVC) <80% predicted with forced expiratory volume in 1 s/FVC ratio >70%.

Results

Among 2213 participants, the median percentage of lung tissue characterised as CT lung injury at a mean age of 40 years was 3.4% (interquartile range 0.8-18.0%). After adjustment for covariates, a 10% higher amount of CT lung injury at mean age 40 years was associated with a 4.37% (95% CI 3.99-4.74%) higher amount of lung tissue characterised as interstitial features at mean age 50 years. Compared to those with the lowest quartile of CT lung injury at mean age 40 years, there were higher odds of incident restrictive spirometry at mean age 55 years in quartile 2 (OR 2.05, 95% CI 1.20-3.48), quartile 3 (OR 2.80, 95% CI 1.66-4.72) and quartile 4 (OR 3.77, 95% CI 2.24-6.33).

Conclusions

CT lung injury is an early objective measure that indicates risk of future lung impairment.

Prognostic value of deep learning-based fibrosis quantification on chest CT in idiopathic pulmonary fibrosis

OBJECTIVE

To investigate the prognostic value of deep learning (DL)-driven CT fibrosis quantification in idiopathic pulmonary fibrosis (IPF).

METHODS

Patients diagnosed with IPF who underwent nonenhanced chest CT and spirometry between 2005 and 2009 were retrospectively collected. Proportions of normal (CT-Norm%) and fibrotic lung volume (CT-Fib%) were calculated on CT using the DL software. The correlations of CT-Norm% and CT-Fib% with forced vital capacity (FVC) and diffusion capacity of carbon monoxide (D_LCO) were evaluated. The multivariable-adjusted hazard ratios (HRs) of CT-Norm% and CT-Fib% for overall survival were calculated with clinical and physiologic variables as covariates using Cox regression. The feasibility of substituting CT-Norm% for D_LCO in the GAP index was investigated using time-dependent areas under the receiver operating characteristic curve (TD-AUCs) at 3 years.

RESULTS

In total, 161 patients (median age [IQR], 68 [62-73] years; 104 men) were evaluated. CT-Norm% and CT-Fib% showed significant correlations with FVC (Pearson's r, 0.40 for CT-Norm% and - 0.37 for CT-Fib%; both p < 0.001) and D_LCO (0.52 for CT-Norm% and - 0.46 for CT-Fib%; both p < 0.001). On multivariable Cox regression, both CT-Norm% and CT-Fib% were independent prognostic factors when adjusted to age, sex, smoking status, comorbid chronic diseases, FVC, and D_LCO (HRs, 0.98 [95% CI 0.97-0.99; p < 0.001] for CT-Norm% at 3 years and 1.03 [1.01-1.05; p = 0.01] for CT-Fib%). Substituting CT-Norm% for D_LCO showed comparable discrimination to the original GAP index (TD-AUC, 0.82 [0.78-0.85] vs. 0.82 [0.79-0.86]; p = 0.75).

CONCLUSION

CT-Norm% and CT-Fib% calculated using chest CT-based deep learning software were independent prognostic factors for overall survival in IPF.

KEY POINTS

• Normal and fibrotic lung volume proportions were automatically calculated using commercial deep learning software from chest CT taken from 161 patients diagnosed with idiopathic pulmonary fibrosis. • CT-quantified volumetric parameters from commercial deep learning software were correlated with forced vital capacity (Pearson's r, 0.40 for normal and - 0.37 for fibrotic lung volume proportions) and diffusion capacity of carbon monoxide (Pearson's r, 0.52 and - 0.46, respectively). • Normal and fibrotic lung volume proportions (hazard ratios, 0.98 and 1.04; both p < 0.001) independently predicted overall survival when adjusted for clinical and physiologic variables.

Machine learning in radiology: the new frontier in interstitial lung diseases

Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes.

Differences in lung and lobe volumes between supine and upright computed tomography in patients with idiopathic lung fibrosis

No clinical study has compared lung or lobe volumes on computed tomography (CT) between the supine and standing positions in patients with idiopathic lung fibrosis (IPF). This study aimed to compare lung and lobe volumes between the supine and standing positions and evaluate the correlations between the supine/standing lung volumes on CT and pulmonary function in patients with IPF. Twenty-three patients with IPF underwent a pulmonary function test and both low-dose conventional (supine position) and upright CT (standing position) during inspiration breath-holds. The volumes of the total lungs and lobes were larger in the standing than in the supine position in patients with IPF (all p < 0.05). Spearman's correlation coefficients between total lung volumes on chest CT in supine/standing positions and vital capacity (VC) or forced VC (FVC) were 0.61/0.79 or 0.64/0.80, respectively. CT-based volumes on upright CT were better correlated with VC and FVC than those on supine CT. Lung and lobe volumes in the standing position may be useful biomarkers to assess disease severity or therapeutic effect in patients with IPF.

How Artificial Intelligence in Imaging Can Better Serve Patients with Bronchial and Parenchymal Lung Diseases?

With the rapid development of computing today, artificial intelligence has become an essential part of everyday life, with medicine and lung health being no exception. Big data-based scientific research does not mean simply gathering a large amount of data and letting the machines do the work by themselves. Instead, scientists need to identify problems whose solution will have a positive impact on patients’ care. In this review, we will discuss the role of artificial intelligence from both physiological and anatomical standpoints, starting with automatic quantitative assessment of anatomical structures using lung imaging and considering disease detection and prognosis estimation based on machine learning. The evaluation of current strengths and limitations will allow us to have a broader view for future developments.

Atlas-Based Lung Segmentation Combined With Automatic Densitometry Characterization In COVID-19 Patients: Training, Validation And First Application In A Longitudinal Study

Purpose

To develop and validate an automated segmentation tool for COVID-19 lung CTs. To combine it with densitometry information in identifying Aerated, Intermediate and Consolidated Volumes in admission (CT1) and follow up CT (CT3).

Materials and Methods

An Atlas was trained on manually segmented CT1 of 250 patients and validated on 10 CT1 of the training group, 10 new CT1 and 10 CT3, by comparing DICE index between automatic (AUTO), automatic-corrected (AUTOMAN) and manual (MAN) contours. A previously developed automatic method was applied on HU lung density histograms to quantify Aerated, Intermediate and Consolidated Volumes. Volumes of subregions in validation CT1 and CT3 were quantified for each method.

Results

In validation CT1/CT3, manual correction of automatic contours was not necessary in 40% of cases. Mean DICE values for both lungs were 0.94 for AUTOVsMAN and 0.96 for AUTOMANVsMAN. Differences between Aerated and Intermediate Volumes quantified with AUTOVsMAN contours were always < 6%. Consolidated Volumes showed larger differences (mean: −95 ± 72 cc). If considering AUTOMANVsMAN volumes, differences got further smaller for Aerated and Intermediate, and were drastically reduced for consolidated Volumes (mean: −36 ± 25 cc). The average time for manual correction of automatic lungs contours on CT1 was 5 ± 2 min.

Conclusions

An Atlas for automatic segmentation of lungs in COVID-19 patients was developed and validated. Combined with a previously developed method for lung densitometry characterization, it provides a fast, operator-independent way to extract relevant quantitative parameters with minimal manual intervention.

Filtration-histogram based texture analysis and CALIPER based pattern analysis as quantitative CT techniques in idiopathic pulmonary fibrosis: head-to-head comparison

OBJECTIVE

To assess the prognostic performance of two quantitative CT (qCT) techniques in idiopathic pulmonary fibrosis (IPF) compared to established clinical measures of disease severity (GAP index).

METHODS

Retrospective analysis of high-resolution CT scans for 59 patients (age 70.5 ± 8.8 years) with two qCT methods. Computer-aided lung informatics for pathology evaluation and ratings based analysis classified the lung parenchyma into six different patterns: normal, ground glass, reticulation, hyperlucent, honeycombing and pulmonary vessels. Filtration histogram-based texture analysis extracted texture features: mean intensity, standard deviation (SD), entropy, mean of positive pixels (MPPs), skewness and kurtosis at different spatial scale filters. Univariate Kaplan-Meier survival analysis assessed the different qCT parameters' performance to predict patient outcome and refine the standard GAP staging system. Multivariate cox regression analysis assessed the independence of the significant univariate predictors of patient outcome.

RESULTS

The predominant parenchymal lung pattern was reticulation (16.6% ± 13.9), with pulmonary vessel percentage being the most predictive of worse patient outcome (p = 0.009). Higher SD, entropy and MPP, in addition to lower skewness and kurtosis at fine texture scale (SSF2), were the most significant predictors of worse outcome (p < 0.001). Multivariate cox regression analysis demonstrated that SD (SSF2) was the only independent predictor of survival (p < 0.001). Better patient outcome prediction was achieved after adding total vessel percentage and SD (SSF2) to the GAP staging system (p = 0.006).

CONCLUSION

Filtration-histogram texture analysis can be an independent predictor of patient mortality in IPF patients.

ADVANCES IN KNOWLEDGE

qCT analysis can help in risk stratifying IPF patients in addition to clinical markers.

Small Airway Reduction and Fibrosis is an Early Pathologic Feature of Idiopathic Pulmonary Fibrosis

RATIONALE

To improve disease outcomes in idiopathic pulmonary fibrosis (IPF) it is essential to understand its early pathophysiology so that it can be targeted therapeutically.

OBJECTIVES

Perform three-dimensional (3D) assessment of the IPF lung micro-structure using stereology and multi-resolution computed tomography (CT) imaging.

METHODS

Explanted lungs from IPF patients (n=8) and donor controls (n=8) were inflated with air and frozen. CT scans were used to assess large airways. Unbiased, systematic uniform random (SUR) samples (n=8/lung) were scanned with microCT for stereological assessment of small airways (number, airway wall and lumen area) and parenchymal fibrosis (volume fraction of tissue, alveolar surface area, and septal wall thickness).

RESULTS

The total number of airways on clinical CT was greater in IPF lungs than control lungs (p<0.01), due to an increase in the wall (p<0.05) and lumen area (p<0.05) resulting in more visible airways with a lumen larger than 2 mm. In IPF tissue samples without microscopic fibrosis, assessed by the volume fraction of tissue using microCT, there was a reduction in the number of the terminal (p<0.01) and transitional (p<0.001) bronchioles, and an increase in terminal bronchiole wall area (p<0.001) compared to control lungs. In IPF tissue samples with microscopic parenchymal fibrosis, terminal bronchioles had increased airway wall thickness (p<0.05), and dilated airway lumens (p<0.001) leading to honeycomb cyst formations.

CONCLUSION

This study has important implications for the current thinking on how the lung tissue is remodeled in IPF, and highlights small airways as a potential target to modify IPF outcomes.

Study protocol for a national cohort of adults focused on respiratory health: the American Lung Association Lung Health Cohort (ALA-LHC) Study

INTRODUCTION

The current framework for investigating respiratory diseases is based on defining lung health as the absence of lung disease. In order to develop a comprehensive approach to prevent the development of lung disease, there is a need to evaluate the full spectrum of lung health spanning from ideal to impaired lung health. The American Lung Association (ALA) Lung Health Cohort is a new, population-based, cohort study focused primarily on characterising lung health in members of the millennial generation without diagnosed severe respiratory disease. Participants will be enrolled for the baseline study visit starting in 2021, and funding will be sought to support future study exams as part of a longitudinal cohort study. This study will be crucial for developing a novel paradigm of lung health throughout the adult life course.

METHODS AND ANALYSIS

This study will leverage the existing infrastructure of the ALA Airways Clinical Research Centers network to enrol 4000 participants between ages 25 and 35 years old at 39 sites across the USA between April 2021 and December 2024. Study procedures will include physical assessment, spirometry, chest CT scan, accelerometry and collection of nasal epithelial lining fluid, nasal epithelial cells, blood and urine. Participants will complete questionnaires about their sociodemographic characteristics, home address histories and exposures, work history and exposure, medical histories, lung health and health behaviours and activity.

ETHICS AND DISSEMINATION

The study was approved by the Johns Hopkins Medicine Institutional Review Board. Findings will be disseminated to the scientific community through peer-reviewed journals and at professional conferences. The lay public will receive scientific findings directly through the ALA infrastructure including the official public website. Deidentified datasets will be deposited to BioLINCC, and deidentified biospecimens may be made available to qualified investigators along with a limited-use datasets.

Automatic lung segmentation in COVID-19 patients: Impact on quantitative computed tomography analysis

Purpose

To assess the impact of lung segmentation accuracy in an automatic pipeline for quantitative analysis of CT images.

Methods

Four different platforms for automatic lung segmentation based on convolutional neural network (CNN), region-growing technique and atlas-based algorithm were considered. The platforms were tested using CT images of 55 COVID-19 patients with severe lung impairment. Four radiologists assessed the segmentations using a 5-point qualitative score (QS). For each CT series, a manually revised reference segmentation (RS) was obtained. Histogram-based quantitative metrics (QM) were calculated from CT histogram using lung segmentationsfrom all platforms and RS. Dice index (DI) and differences of QMs (ΔQMs) were calculated between RS and other segmentations.

Results

Highest QS and lower ΔQMs values were associated to the CNN algorithm. However, only 45% CNN segmentations were judged to need no or only minimal corrections, and in only 17 cases (31%), automatic segmentations provided RS without manual corrections. Median values of the DI for the four algorithms ranged from 0.993 to 0.904. Significant differences for all QMs calculated between automatic segmentations and RS were found both when data were pooled together and stratified according to QS, indicating a relationship between qualitative and quantitative measurements. The most unstable QM was the histogram 90th percentile, with median ΔQMs values ranging from 10HU and 158HU between different algorithms.

Conclusions

None of tested algorithms provided fully reliable segmentation. Segmentation accuracy impacts differently on different quantitative metrics, and each of them should be individually evaluated according to the purpose of subsequent analyses.

The evolution of computer-based analysis of high-resolution CT of the chest in patients with IPF

In patients with idiopathic pulmonary fibrosis (IPF), there is an urgent need of biomarkers which can predict disease behaviour or response to treatment. Most published studies report results based on continuous data which can be difficult to apply to individual patients in clinical practice. Having antifibrotic therapies makes it even more important that we can accurately diagnose and prognosticate in IPF patients. Advances in computer technology over the past decade have provided computer-based methods for objectively quantifying fibrotic lung disease on high-resolution CT of the chest with greater strength than visual CT analysis scores. These computer-based methods and, more recently, the arrival of deep learning-based image analysis might provide a response to these unsolved problems. The purpose of this commentary is to provide insights into the problems associated with visual interpretation of HRCT, describe of the current technologies used to provide quantification of disease on HRCT and prognostication in IPF patients, discuss challenges to the implementation of this technology and future directions.

Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds

CT patterns of viral pneumonia are usually only qualitatively described in radiology reports. Artificial intelligence enables automated and reliable segmentation of lungs with chest CT. Based on this, the purpose of this study was to derive meaningful imaging biomarkers reflecting CT patterns of viral pneumonia and assess their potential to discriminate between healthy lungs and lungs with viral pneumonia. This study used non-enhanced and CT pulmonary angiograms (CTPAs) of healthy lungs and viral pneumonia (SARS-CoV-2, influenza A/B) identified by radiology reports and RT-PCR results. After deep learning segmentation of the lungs, histogram-based and threshold-based analyses of lung attenuation were performed and compared. The derived imaging biomarkers were correlated with parameters of clinical and biochemical severity (modified WHO severity scale; c-reactive protein). For non-enhanced CTs (n = 526), all imaging biomarkers significantly differed between healthy lungs and lungs with viral pneumonia (all p < 0.001), a finding that was not reproduced for CTPAs (n = 504). Standard deviation (histogram-derived) and relative high attenuation area [600-0 HU] (HU-thresholding) differed most. The strongest correlation with disease severity was found for absolute high attenuation area [600-0 HU] (r = 0.56, 95% CI = 0.46-0.64). Deep-learning segmentation-based histogram and HU threshold analysis could be deployed in chest CT evaluation for the differentiating of healthy lungs from AP lungs.

Fully Automated Segmentation of Pulmonary Fibrosis Using Different Software Tools

OBJECTIVE

Evaluation of software tools for segmentation, quantification, and characterization of fibrotic pulmonary parenchyma changes will strengthen the role of CT as biomarkers of disease extent, evolution, and response to therapy in idiopathic pulmonary fibrosis (IPF) patients.

METHODS

418 nonenhanced thin-section MDCTs of 127 IPF patients and 78 MDCTs of 78 healthy individuals were analyzed through 3 fully automated, completely different software tools: YACTA, LUFIT, and IMBIO. The agreement between YACTA and LUFIT on segmented lung volume and 80th (reflecting fibrosis) and 40th (reflecting ground-glass opacity) percentile of the lung density histogram was analyzed using Bland-Altman plots. The fibrosis and ground-glass opacity segmented by IMBIO (lung texture analysis software tool) were included in specific regression analyses.

RESULTS

In the IPF-group, LUFIT outperformed YACTA by segmenting more lung volume (mean difference 242 mL, 95% limits of agreement -54 to 539 mL), as well as quantifying higher 80th (76 HU, -6 to 158 HU) and 40th percentiles (9 HU, -73 to 90 HU). No relevant differences were revealed in the control group. The 80th/40th percentile as quantified by LUFIT correlated positively with the percentage of fibrosis/ground-glass opacity calculated by IMBIO (r = 0.78/r = 0.92).

CONCLUSIONS

In terms of segmentation of pulmonary fibrosis, LUFIT as a shape model-based segmentation software tool is superior to the threshold-based YACTA, tool, since the density of (severe) fibrosis is similar to that of the surrounding soft tissues. Therefore, shape modeling as used in LUFIT may serve as a valid tool in the quantification of IPF, since this mainly affects the subpleural space.

Quantification of dual-energy CT-derived functional parameters as potential imaging markers for progression of idiopathic pulmonary fibrosis

OBJECTIVES

The individual course of disease in idiopathic pulmonary fibrosis (IPF) is highly variable. Assessment of disease activity and prospective estimation of disease progression might have the potential to improve therapy management and indicate the onset of treatment at an earlier stage. The aim of this study was to evaluate whether regional ventilation, lung perfusion, and late enhancement can serve as early imaging markers for disease progression in patients with IPF.

METHODS

In this retrospective study, contrast-enhanced dual-energy CT scans of 32 patients in inspiration and delayed expiration were performed at two time points with a mean interval of 15.4 months. The pulmonary blood volume (PBV) images obtained in the arterial and delayed perfusion phase served as a surrogate for arterial lung perfusion and parenchymal late enhancement. The virtual non-contrast (VNC) images in inspiration and expiration were non-linearly registered to provide regional ventilation images. Image-derived parameters were correlated with longitudinal changes of lung function (FVC%, DLCO%), mean lung density in CT, and CT-derived lung volume.

RESULTS

Regional ventilation and late enhancement at baseline preceded future change in lung volume (R - 0.474, p 0.006/R - 0.422, p 0.016, respectively) and mean lung density (R - 0.469, p 0.007/R - 0.402, p 0.022, respectively). Regional ventilation also correlated with a future change in FVC% (R - 0.398, p 0.024).

CONCLUSION

CT-derived functional parameters of regional ventilation and parenchymal late enhancement are potential early imaging markers for idiopathic pulmonary fibrosis progression.

KEY POINTS

• Functional CT parameters at baseline (regional ventilation and late enhancement) correlate with future structural changes of the lung as measured with loss of lung volume and increase in lung density in serial CT scans of patients with idiopathic pulmonary fibrosis. • Functional CT parameter measurements in high-attenuation areas (- 600 to - 250 HU) are significantly different from normal-attenuation areas (- 950 to - 600 HU) of the lung. • Mean regional ventilation in functional CT correlates with a future change in forced vital capacity (FVC) in pulmonary function tests.

Improving clinical disease subtyping and future events prediction through a chest CT-based deep learning approach

PURPOSE

To develop and evaluate a deep learning (DL) approach to extract rich information from high-resolution computed tomography (HRCT) of patients with chronic obstructive pulmonary disease (COPD).

METHODS

We develop a DL-based model to learn a compact representation of a subject, which is predictive of COPD physiologic severity and other outcomes. Our DL model learned: (a) to extract informative regional image features from HRCT; (b) to adaptively weight these features and form an aggregate patient representation; and finally, (c) to predict several COPD outcomes. The adaptive weights correspond to the regional lung contribution to the disease. We evaluate the model on 10 300 participants from the COPDGene cohort.

RESULTS

Our model was strongly predictive of spirometric obstruction ( r 2  =  0.67) and grouped 65.4% of subjects correctly and 89.1% within one stage of their GOLD severity stage. Our model achieved an accuracy of 41.7% and 52.8% in stratifying the population-based on centrilobular (5-grade) and paraseptal (3-grade) emphysema severity score, respectively. For predicting future exacerbation, combining subjects' representations from our model with their past exacerbation histories achieved an accuracy of 80.8% (area under the ROC curve of 0.73). For all-cause mortality, in Cox regression analysis, we outperformed the BODE index improving the concordance metric (ours: 0.61 vs BODE: 0.56).

CONCLUSIONS

Our model independently predicted spirometric obstruction, emphysema severity, exacerbation risk, and mortality from CT imaging alone. This method has potential applicability in both research and clinical practice.

A patient-specific approach for quantitative and automatic analysis of computed tomography images in lung disease: Application to COVID-19 patients

PURPOSE

Quantitative metrics in lung computed tomography (CT) images have been widely used, often without a clear connection with physiology. This work proposes a patient-independent model for the estimation of well-aerated volume of lungs in CT images (WAVE).

METHODS

A Gaussian fit, with mean (Mu.f) and width (Sigma.f) values, was applied to the lower CT histogram data points of the lung to provide the estimation of the well-aerated lung volume (WAVE.f). Independence from CT reconstruction parameters and respiratory cycle was analysed using healthy lung CT images and 4DCT acquisitions. The Gaussian metrics and first order radiomic features calculated for a third cohort of COVID-19 patients were compared with those relative to healthy lungs. Each lung was further segmented in 24 subregions and a new biomarker derived from Gaussian fit parameter Mu.f was proposed to represent the local density changes.

RESULTS

WAVE.f resulted independent from the respiratory motion in 80% of the cases. Differences of 1%, 2% and up to 14% resulted comparing a moderate iterative strength and FBP algorithm, 1 and 3 mm of slice thickness and different reconstruction kernel. Healthy subjects were significantly different from COVID-19 patients for all the metrics calculated. Graphical representation of the local biomarker provides spatial and quantitative information in a single 2D picture.

CONCLUSIONS

Unlike other metrics based on fixed histogram thresholds, this model is able to consider the inter- and intra-subject variability. In addition, it defines a local biomarker to quantify the severity of the disease, independently of the observer.

[Radiological features of interstitial lung diseases]

In addition to pneumology and pathology, radiology is an essential discipline in the interdisciplinary diagnosis of interstitial lung diseases (ILDs). The gold standard for diagnosis of ILD is computed tomography. Diagnostic findings are based on specific radiological signs such as interlobular septal thickening and nodular changes. From these signs and their distribution within the lung, radiological patterns can be derived, e.g., usual interstitial pneumonia, nonspecific interstitial pneumonia, or organizing pneumonia. Various differential diagnoses result from the radiological pattern, which can then be further limited in an interdisciplinary manner with the clinic and pathology and, if necessary, trigger further diagnostics.The visual assessment of interstitial lung changes requires experience and training and is nevertheless error-prone with high inter- and intraobserver variabilities. Recently, therefore, computer-aided analysis of ILDs has been increasingly promoted. These computer programs analyze the density distribution of the lung parenchyma using parameters such as mean lung density, skewness, and kurtosis thus enabling the quantification and assessment of the course of disease. Furthermore, texture analysis and artificial intelligence are used to characterize parenchymal changes and differentiate between regions of ground glass, reticulation, and honeycombing. Modern dual-energy CT methods allow a combined, regional recording of both the morphology and the function and provide information about regional ventilation and perfusion.

Quantitative CT imaging and advanced visualization methods: potential application in novel coronavirus disease 2019 (COVID-19) pneumonia

Increasingly, quantitative lung computed tomography (qCT)-derived metrics are providing novel insights into chronic inflammatory lung diseases, including chronic obstructive pulmonary disease, asthma, interstitial lung disease, and more. Metrics related to parenchymal, airway, and vascular anatomy together with various measures associated with lung function including regional parenchymal mechanics, air trapping associated with functional small airways disease, and dual-energy derived measures of perfused blood volume are offering the ability to characterize disease phenotypes associated with the chronic inflammatory pulmonary diseases. With the emergence of COVID-19, together with its widely varying degrees of severity, its rapid progression in some cases, and the potential for lengthy post-COVID-19 morbidity, there is a new role in applying well-established qCT-based metrics. Based on the utility of qCT tools in other lung diseases, previously validated supervised classical machine learning methods, and emerging unsupervised machine learning and deep-learning approaches, we are now able to provide desperately needed insight into the acute and the chronic phases of this inflammatory lung disease. The potential areas in which qCT imaging can be beneficial include improved accuracy of diagnosis, identification of clinically distinct phenotypes, improvement of disease prognosis, stratification of care, and early objective evaluation of intervention response. There is also a potential role for qCT in evaluating an increasing population of post-COVID-19 lung parenchymal changes such as fibrosis. In this work, we discuss the basis of various lung qCT methods, using case-examples to highlight their potential application as a tool for the exploration and characterization of COVID-19, and offer scanning protocols to serve as templates for imaging the lung such that these established qCT analyses have the best chance at yielding the much needed new insights.

Quantitative Evaluation of Fibrosis in IPF Patients: Meaning of Diffuse Pulmonary Ossification

To investigate the role of diffuse pulmonary ossification (DPO) in disease severity in a population of Idiopathic Pulmonary Fibrosis (IPF) patients. This retrospective study was carried out on 95 IPF patients-44 with DPO on high resolution computed tomography (HRCT) and 51 with no calcifications detected on HRCT. Pulmonary Function Tests (PFTs) acquired nearest to the HRCT were collected. Images were analyzed by two radiologists using a qualitative method, based on HRCT fibrosis visual score, and using a quantitative method, based on histogram-based analysis. The Spearman's rank correlation coefficient was used to measure the strength and direction of the linear relationship between HRCT fibrosis score and PFTs; in addition, Spearman's rank correlation coefficient was used to explore the relationships between HRCT fibrosis score and quantitative index and between quantitative indexes and PFTs. A weak correlation between HRCT fibrosis score and PFTs was proven (r =-0.014 and p = 0.9347 for FVC (Forced Vital Capacity), r = -0.379 and p = 0.0174 for DLCO (Carbon monoxide diffusing capacity)). We found a moderate negative correlation between HRCT fibrosis score and kurtosis (r = -0.448, p = 0.004272) and skewness (r = -0.463, p = 0.003019) and a weak positive correlation with High Attenuation Area (HAA)% (r = 0.362, p = 0.0235). Moreover, a moderate linear correlation between Quantitative Indexes and FVC (r = 0.577, p = 0.000051 for kurtosis and FVC, r = 0.598, p = 0.000023 for skewness and FVC, r = -0.519, p = 0.0000364 for HAA% and FVC) and between quantitative indexes and DLCO (r = 0.469, p = 0.001508 for kurtosis, and DLCO, r = 0.474, p = 0.001309 for skewness and DLCO, r = -0.412, p = 0.005996 for HAA% and DLCO) was revealed. To better investigate the influence of DPO in disease progression, a longitudinal evaluation should be performed.

Computer-aided analysis in evaluation and grading of interstitial lung diseases in correlation with CT-based visual scoring and pulmonary function tests

Background

Interstitial lung diseases (ILDs) represent a large group of more than 200 different entities. High resolution computed tomography (HRCT) is accepted as the gold standard imaging modality in the diagnosis of ILD. The visual-based scoring offers an advantage in finding a specific type of ILD. Computer-aided CT attenuation histogram is another way of characterizing and quantifying diffuse lung disease. The histogram analysis (HIST) consists of calculating skewness, kurtosis, and mean lung density to quantify lung disease and monitor progression. The aim of our study was to investigate the value of computer-aided analysis of HRCT for interstitial lung diseases in correlation with scoring and pulmonary function tests.

Results

This prospective study included 50 patients with suspected ILD. The mean age of patients was 46.7 years ± 12.5. Mean forced expiratory volume FEV1 was 63.6 ± 20.9. HRCT examination was done for all patients followed by CT-based visual scaling. Most of the studied patients (43.3%) had a CT visual semi-quantitative scoring ranged between 40 and 64. CT-based lung density histograms (LDH) were obtained for all patients using the 3D Slicer Software (Chest Imaging Platform). There was a significant difference between patient’s groups of different (mild, moderate, and severe) grades of ILD according to FEV1 regarding MLD, skewness, and kurtosis of corresponding CT-based density histograms (p values < 0.001). More significant and higher correlation was observed between computerized aided CT quantified mean lung densities (MLD) and (FEV1) (p value < 0.001 and r = − 0.570). The ROC curve analysis demonstrated good performance for CT visual scoring with PFT (AUC = 0.71); a cutoff scoring 15 or higher was associated with best sensitivity (75%) and specificity (100%). Meanwhile, ROC curve analysis for MLD and FEV1 demonstrated an excellent performance for computer-based CT quantification (AUC = 0.85) with a value of − 769 HU which increased sensitivity to 65% and specificity to 100%.

Conclusion

Visual-based scoring techniques offer an advantage in finding a specific type of ILD. Computer-based quantification system could be a means for accurately monitoring the disease progression or response to therapy.

Comparative analysis of density histograms and visual scores in incremental and volumetric high-resolution computed tomography of the chest in idiopathic pulmonary fibrosis patients

Background

Volumetric high-resolution computed tomography (HRCT) of the chest has recently replaced incremental CT in the diagnostic workup of idiopathic pulmonary fibrosis (IPF). Concomitantly, visual and quantitative scores have been proposed for disease extent assessment to ameliorate disease management.

Purpose

To compare the performance of density histograms (mean lung attenuation, skewness, and kurtosis) and visual scores, along with lung function correlations, in IPF patients submitted to incremental or volumetric thorax HRCT.

Material and methods

Clinical data and CT scans of 89 newly diagnosed and therapy-naive IPF patients were retrospectively evaluated.

Results

Forty-six incremental and 43 volumetric CT scans were reviewed. No differences of density histograms and visual scores estimates were found by comparing two HRCT techniques, with an optimal inter-operator agreement (concordance correlation coefficient >0.90 in all instances). Single-breath diffusing lung capacity for carbon monoxide (DLCO_sb) was inversely related with the Best score (r = −00.416; p = 0.014), the Kazerooni fibrosis extent (r = −0.481; p = 0.004) and the mean lung attenuation (r = −0.382; p = 0.026), while a positive correlation was observed with skewness (r = 0.583; p = 0.001) and kurtosis (r = 0.543; p = 0.001) in the incremental HRCT sub-group. Similarly, in the volumetric CT sub-cohort, DLCO_sb was significantly associated with skewness (r = 0.581; p = 0.007) and kurtosis (r = 0.549; p = 0.018). Correlations with visual scores were not confirmed. Forced vital capacity significantly related to all density indices independently on HRCT technique.

Conclusions

Density histograms and visual scores similarly perform in incremental and volumetric HRCT. Density quantification displays an optimal reproducibility and proves to be superior to visual scoring as more strongly correlated with lung function.

Association of quantitative CT lung density measurements and lung function decline in World Trade Center workers

BACKGROUND

Occupational exposures at the WTC site after 11 September 2001 have been associated with presumably inflammatory chronic lower airway diseases.

AIMS

In this study, we describe the trajectories of expiratory air flow decline, identify subgroups with adverse progression, and investigate the association of those trajectories with quantitative computed tomography (QCT) imaging measurement of increased and decreased lung density.

METHODS

We examined the trajectories of expiratory air flow decline in a group of 1,321 former WTC workers and volunteers with at least three periodic spirometries, and using QCT-measured low (LAV%, -950 HU) and high (HAV%, from -600 to -250 HU) attenuation volume percent. We calculated the individual regression line slopes for first-second forced expiratory volume (FEV₁ slope), identified subjects with rapidly declining ("accelerated decliners") and increasing ("improved"), and compared them to subjects with "intermediate" (0 to -66.5 mL/year) FEV₁ slope. We then used multinomial logistic regression to model those three trajectories, and the two lung attenuation metrics.

RESULTS

The mean longitudinal FEV₁ slopes for the entire study population, and its intermediate, decliner, and improved subgroups were, respectively, -40.4, -34.3, -106.5, and 37.6 mL/year. In unadjusted and adjusted analyses, LAV% and HAV% were both associated with "accelerated decliner" status (OR_adj , 95% CI 2.37, 1.41-3.97, and 1.77, 1.08-2.89, respectively), compared to the intermediate decline.

CONCLUSIONS

Longitudinal FEV₁ decline in this cohort, known to be associated with QCT proximal airway inflammation metric, is also associated with QCT indicators of increased and decreased lung density. The improved FEV₁ trajectory did not seem to be associated with lung density metrics.

Interstitial Lung Disease in Relatives of Patients with Pulmonary Fibrosis

Rationale: Although relatives of patients with familial pulmonary fibrosis (FPF) are at an increased risk for interstitial lung disease (ILD), the risk among relatives of sporadic idiopathic pulmonary fibrosis (IPF) is not known.Objectives: To identify the prevalence of interstitial lung abnormalities (ILA) and ILD among relatives of patients with FPF and sporadic IPF.Methods: Undiagnosed first-degree relatives of patients with pulmonary fibrosis (PF) consented to participate in a screening study that included the completion of questionnaires, pulmonary function testing, chest computed tomography, a blood sample collection for immunophenotyping, telomere length assessments, and genetic testing.Measurements and Main Results: Of the 105 relatives in the study, 33 (31%) had ILA, whereas 72 (69%) were either indeterminate or had no ILA. Of the 33 relatives with ILA, 19 (58%) had further evidence for ILD (defined by the combination of imaging findings and pulmonary function testing decrements). There was no evidence in multivariable analyses that the prevalence of either ILA or ILD differed between the 46 relatives with FPF and the 59 relatives with sporadic IPF. Relatives with decrements in either total lung or diffusion capacity had a greater than 9-fold increase in their odds of having ILA (odds ratio, 9.6; 95% confidence interval, 3.1-29.8; P < 0.001).Conclusions: An undiagnosed form of ILD may be present in greater than 1 in 6 older first-degree relatives of patients with PF. First-degree relatives of patients with both familial and sporadic IPF appear to be at similar risk. Our findings suggest that screening for PF in relatives might be warranted.

Increased Airway Wall Thickness in Interstitial Lung Abnormalities and Idiopathic Pulmonary Fibrosis

RATIONALE

There is increasing evidence that aberrant processes occurring in the airways may precede the development of idiopathic pulmonary fibrosis (IPF); however, there has been no prior confirmatory data derived from imaging studies.

OBJECTIVES

To assess quantitative measures of airway wall thickness (AWT) in populations characterized for interstitial lung abnormalities (ILA) and for IPF.

METHODS

Computed tomographic imaging of the chest and measures of AWT were available for 6,073, 615, 1,167, and 38 participants from COPDGene (Genetic Epidemiology of COPD study), ECLIPSE (Evaluation of COPD Longitudinally to Identify Predictive Surrogate Endpoints study), and the Framingham Heart Study (FHS) and in patients with IPF from the Brigham and Women's Hospital Herlihy Registry, respectively. To evaluate these associations, we used multivariable linear regression to compare a standardized measure of AWT (the square root of AWT for airways with an internal perimeter of 10 mm [Pi10]) and characterizations of ILA and IPF by computed tomographic imaging of the chest.

RESULTS

In COPDGene, ECLIPSE, and FHS, research participants with ILA had increased measures of Pi10 compared with those without ILA. Patients with IPF had mean measures of Pi10 that were even greater than those noted in research participants with ILA. After adjustment for important covariates (e.g., age, sex, race, body mass index, smoking behavior, and chronic obstructive pulmonary disease severity when appropriate), research participants with ILA had increased measures of Pi10 compared with those without ILA (0.03 mm in COPDGene, 95% confidence interval [CI], 0.02-0.03; P < 0.001; 0.02 mm in ECLIPSE, 95% CI, 0.005-0.04; P = 0.01; 0.07 mm in FHS, 95% CI, 0.01-0.1; P = 0.01). Compared with COPDGene participants without ILA older than 60 years of age, patients with IPF were also noted to have increased measures of Pi10 (2.0 mm, 95% CI, 2.0-2.1; P < 0.001). Among research participants with ILA, increases in Pi10 were correlated with reductions in lung volumes in some but not all populations.

CONCLUSIONS

These results demonstrate that measurable increases in AWT are consistently noted in research participants with ILA and in patients with IPF. These findings suggest that abnormalities of the airways may play a role in, or be correlated with, early pathogenesis of pulmonary fibrosis.

Performance of Radiomics Features in the Quantification of Idiopathic Pulmonary Fibrosis from HRCT

BACKGROUND

Our study assesses the diagnostic value of different features extracted from high resolution computed tomography (HRCT) images of patients with idiopathic pulmonary fibrosis. These features are investigated over a range of HRCT lung volume measurements (in Hounsfield Units) for which no prior study has yet been published. In particular, we provide a comparison of their diagnostic value at different Hounsfield Unit (HU) thresholds, including corresponding pulmonary functional tests.

METHODS

We consider thirty-two patients retrospectively for whom both HRCT examinations and spirometry tests were available. First, we analyse the HRCT histogram to extract quantitative lung fibrosis features. Next, we evaluate the relationship between pulmonary function and the HRCT features at selected HU thresholds, namely -200 HU, 0 HU, and +200 HU. We model the relationship using a Poisson approximation to identify the measure with the highest log-likelihood.

RESULTS

Our Poisson models reveal no difference at the -200 and 0 HU thresholds. However, inferential conclusions change at the +200 HU threshold. Among the HRCT features considered, the percentage of normally attenuated lung at -200 HU shows the most significant diagnostic utility.

CONCLUSIONS

The percentage of normally attenuated lung can be used together with qualitative HRCT assessment and pulmonary function tests to enhance the idiopathic pulmonary fibrosis (IPF) diagnostic process.

Clinical judgment versus lung allocation score in predicting lung transplant waitlist mortality

Canadian lung transplant centers currently use a subjective and dichotomous "Status" ranking to prioritize waitlisted patients for lung transplantation. The lung allocation score (LAS) is an objective composite score derived from clinical parameters associated with both waitlist and post-transplant survival. We performed a retrospective cohort study to determine whether clinical judgment (Status) or LAS better predicted waitlist mortality. All adult patients listed for lung transplantation between 2007 and 2012 at three Canadian lung transplant programs were included. Status and LAS were compared in their ability to predict waitlist mortality using Cox proportional hazards models and C-statistics. Status and LAS were available for 1122 patients. Status 2 patients had a higher LAS compared to Status 1 patients (mean 40.8 (4.4) vs 34.6 (12.5), P = .0001). Higher LAS was associated with higher risk of waitlist mortality (HR 1.06 per unit LAS, 95% CI 1.05, 1.07, P < .001). LAS predicted waitlist mortality better than Status (C-statistic 0.689 vs 0.674). Patients classified as Status 2 and LAS ≥ 37 had the worst survival awaiting transplant, HR of 8.94 (95% CI 5.97, 13.37). LAS predicted waitlist mortality better than Status; however, the best predictor of waitlist mortality may be a combination of both LAS and clinical judgment.

[Artificial intelligence in lung imaging]

CLINICAL/METHODICAL ISSUE

Artificial intelligence (AI) has the potential to improve diagnostic accuracy and management in patients with lung disease through automated detection, quantification, classification, and prediction of disease progression.

STANDARD RADIOLOGICAL METHODS

Owing to unspecific symptoms, few well-defined CT disease patterns, and varying prognosis, interstitial lungs disease represents a focus of AI-based research.

METHODICAL INNOVATIONS

Supervised and unsupervised machine learning can identify CT disease patterns using features which may allow the analysis of associations with specific diseases and outcomes.

PERFORMANCE

Machine learning on the one hand improves computer-aided detection of pulmonary nodules. On the other hand it enables further characterization of pulmonary nodules, which may improve resource effectiveness regarding lung cancer screening programs.

ACHIEVEMENTS

There are several challenges regarding AI-based CT data analysis. Besides the need for powerful algorithms, expert annotations and extensive training data sets that reflect physiologic and pathologic variability are required for effective machine learning. Comparability and reproducibility of AI research deserve consideration due to a lack of standardization in this emerging field.

PRACTICAL RECOMMENDATIONS

This review article presents the state of the art and the challenges concerning AI in lung imaging with special consideration of interstitial lung disease, and detection and consideration of pulmonary nodules.

Classification of Interstitial Lung Abnormality Patterns with an Ensemble of Deep Convolutional Neural Networks

Subtle interstitial changes in the lung parenchyma of smokers, known as Interstitial Lung Abnormalities (ILA), have been associated with clinical outcomes, including mortality, even in the absence of Interstitial Lung Disease (ILD). Although several methods have been proposed for the automatic identification of more advanced Interstitial Lung Disease (ILD) patterns, few have tackled ILA, which likely precedes the development ILD in some cases. In this context, we propose a novel methodology for automated identification and classification of ILA patterns in computed tomography (CT) images. The proposed method is an ensemble of deep convolutional neural networks (CNNs) that detect more discriminative features by incorporating two, two-and-a-half and three- dimensional architectures, thereby enabling more accurate classification. This technique is implemented by first training each individual CNN, and then combining its output responses to form the overall ensemble output. To train and test the system we used 37424 radiographic tissue samples corresponding to eight different parenchymal feature classes from 208 CT scans. The resulting ensemble performance including an average sensitivity of 91,41% and average specificity of 98,18% suggests it is potentially a viable method to identify radiographic patterns that precede the development of ILD.

Assessment of Lung Cancer Development in Idiopathic Pulmonary Fibrosis Patients Using Quantitative High-Resolution Computed Tomography: A Retrospective Analysis

PURPOSE

The purpose of this study was to investigate histogram-based quantitative high-resolution computed tomography (HRCT) indexes in the assessment of lung cancer (LC) development in idiopathic pulmonary fibrosis (IPF) patients.

MATERIALS AND METHODS

From IPF databases of 2 national respiratory centers, we retrospectively studied patients with and without LC development-respectively, divided into Group A (n=16) and Group B (n=33). The extent of fibrotic disease was quantified on baseline and follow-up HRCT examinations using kurtosis, skewness, percentage of high attenuation area (HAA%), and percentage of fibrotic area (FA%). These indexes were compared between the 2 groups using the Mann-Whitney U test. In the prediction of LC development, receiver operating characteristic analysis was performed to assess threshold values of HRCT indexes.

RESULTS

At baseline, no difference was reported among groups for kurtosis, skewness, HAA%, and FA%, with P-values of 0.0881, 0.0606, 0.0578, and 0.0606, respectively. On follow-up, significant differences were reported, with P-values of 0.0174 for kurtosis, 0.0313 for skewness, 0.0297 for HAA%, and 0.0407 for FA%.On baseline HRCT, in the prediction of LC development, receiver operating characteristic analysis reported sensibility and specificity of 87.5% and 45.45% for kurtosis, 68.75% and 63.64% for skewness, 81.25% and 54.55% for FA%, and 75% and 60.61% for HAA%.

CONCLUSIONS

LC development is associated with progression of fibrosis; at baseline, FA% and HAA% reported more convenient sensitivity/specificity ratios in the prediction of LC development.